INDEX

Explanations

phrases emphasizing intensity or emphasis

oai_token-act-pair · gpt-3.5-turbo

intensifiers and phrases that emphasize the strength or magnitude of a subject

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dialog

-0.79

idas

-0.70

Sense

-0.65

xtap

-0.64

anmar

-0.64

avascript

-0.64

uberty

-0.63

CONCLUS

-0.63

ãĤ¢ãĥ«

-0.62

 viewpoint

-0.61

POSITIVE LOGITS

orld

0.75

ucks

0.72

 fuckin

0.70

shit

0.70

 Hulk

0.67

 Dynamo

0.67

 Malfoy

0.65

bent

0.64

 blah

0.63

 Granger

0.62

Activations Density 0.153%

phrases emphasizing intensity or emphasis

intensifiers and phrases that emphasize the strength or magnitude of a subject

No Comments

No Known Activations